Goals

A goal describes an outcome for one or more AI agents to pursue. It provides a shared definition of success while leaving execution details to the agents responsible for the work.

Goals should be specific enough to evaluate, durable across individual agent runs, and explicit about any constraints that affect completion.

Each goal belongs to an organization and records a short title, a long-form detailed description that may contain Markdown, an accountable organization member, an ordered list of titled success criteria, and a lifecycle status: active, paused, completed, or archived. Organization-defined labels provide stable taxonomy and can be renamed without changing goal references.

Status is a projection of an append-only update sequence. Creating a goal records revision 1; every subsequent status report supplies a summary, a long-form Markdown-capable description, the expected current revision, and an idempotency key. Appending the report and advancing the goal's status and revision happen atomically. Metadata updates cannot change status, and goals are archived through a status report rather than hard-deleted.

Each update records the authorizing user separately from the immediate actor. The actor can be a user, client, or verified agent, with an optional agent run identifier. Authentication provenance records the verified session, API-token record, or OAuth client that established authority. MCP client name and version are retained only as descriptive client metadata; self-reported values do not establish identity.